© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13549
    Prev
    Next
    INDEX
    Explanations

    mentions of time periods or durations expressed in numbers and months.

    oai_token-act-pair · gemini-2.0-flash

    patterns related to time intervals and schedules

    np_token-act-pair-logits · gpt-4o-mini

    spans of time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     year
    -1.40
    year
    -1.26
     Year
    -1.23
     jaar
    -1.21
    Year
    -1.19
     YEAR
    -1.18
     año
    -1.14
     tahun
    -1.07
    YEAR
    -1.05
     annually
    -1.02
    POSITIVE LOGITS
    aarrggbb
    0.63
     monthly
    0.62
     Monthly
    0.61
    Monthly
    0.52
     weeks
    0.52
     ten
    0.52
     Weeks
    0.52
     eight
    0.51
     Month
    0.51
    OfWeek
    0.51
    Activations Density 2.274%

    No Known Activations